Amazon Comprehend Now Supports Confusion Matrices for Custom Classification

Amazon Comprehend helps you solve a variety of use cases with custom classification. For example, you can build classifiers to organize your daily customer feedback into categories like “loyalty”, “sales” or “product defect”. Amazon Comprehend removes the complexity to create custom classification models, requiring only a CSV file with labels and example text. A confusion matrix helps you understand how your labels are performing based on the training data you provided. For example, if you have two labels with similar training content, the custom classification model may not be able to clearly distinguish between these labels. Using the confusion matrix, you can focus on creating better training content, so each label is more distinct from the other.
Get started with Amazon Comprehend custom classification models here and learn more about how to use a confusion matrix as part of training your model here.
Quelle: aws.amazon.com

Announcing Azure to AWS migration support in AWS Server Migration Service

AWS Server Migration Service (SMS) now offers support for migrating virtual machines (VMs) running in Microsoft Azure to the AWS cloud. The new capability makes it easier for you to migrate existing applications running in Microsoft Azure to the AWS cloud to take advantage of greater reliability, faster performance, more security capabilities, and lower costs.  
Quelle: aws.amazon.com

Amazon Polly Adds Arabic Language Support

Amazon Polly is a service that turns text into lifelike speech. Today, we are excited to announce Zeina, the first Arabic voice for Amazon Polly. Zeina is a clear and natural-sounding female voice.
Used by over 400 million people, Arabic is one of the most spoken languages in the world. It consists of 30 dialects, including its universal form, which is Modern Standard Arabic (MSA). Zeina follows the MSA pronunciation, which is the common broadcasting standard across the region. MSA might sometimes sound formal because it differs from day-to-day speaking style. However, it’s the linguistic thread that links the Arabic native-speakers worldwide.
Amazon Polly customers who plan to use Zeina’s voice include Emirates NBD – a leading bank in the Middle East who has introduced an AI powered virtual assistant, Duolingo – a globally operating eLearning platform offering a portfolio of 84 language courses for more than 30 distinct languages, and iTranslate – a leading translation and dictionary app that offers text translation as well as voice-to-voice conversations in over 100 languages.
With the addition of Arabic language support, the Amazon Polly portfolio now includes 59 voices across 29 languages. You can check out the full list in the Voices in Amazon Polly section of our documentation.
Quelle: aws.amazon.com

AWS Transit Gateway is Now Available in the AWS GovCloud (US) Regions

AWS Transit Gateway is now available in both AWS GovCloud (US) Regions. AWS Transit Gateway enables customers to connect thousands of Amazon Virtual Private Clouds (Amazon VPCs) and their on-premises networks using a single gateway. As you grow the number of workloads across multiple AWS accounts, you need to scale your networks, better control your policies, and effectively monitor your resources.  
Quelle: aws.amazon.com

Amazon FreeRTOS Now Supports Resource Tagging

You can now assign tags to Amazon FreeRTOS Over-The-Air (OTA) update and customer configuration resources. This helps to search and manage access control of these resource based on resource tagging. This support builds upon previously-released support for resource tagging in AWS IoT Core.
Quelle: aws.amazon.com

Amplify Framework Announces New Amazon Aurora Serverless, GraphQL, and OAuth Capabilities

Starting today, Amplify Framework includes support for adding Amazon Aurora Serverless as a data source for your AWS AppSync GraphQL APIs when building mobile and web applications. This enables developers to use the Amplify CLI, part of the Amplify Framework, to generate a GraphQL API with auto-generated schema and resolvers that works with an existing Aurora Serverless database. Previously, developers had to setup an AWS Lambda function to use Aurora Serverless as a data source for a GraphQL API.
The GraphQL Transform library, included in the Amplify CLI, provides a simple abstraction that helps developers quickly create scalable web and mobile backends on AWS. This release adds features to the GraphQL Transform Library that enable developers to provide fine-grained access control across their APIs by configuring authorization rules for top level and individual fields. In addition, developers can configure access to connected fields inside a model, or those that represent relationships between data. Previously, access rules were only applied to top-level fields and there was no way to configure access to individual and connected fields.
This release also allows developers using the Amplify JavaScript library to trigger OAuth flows in their web applications with a single line of code. Developers can choose between using Amazon Cognito Hosted UI or their own UI while still having the ability to federate with User Pools and get AWS credentials to access their resources.
To learn more about AWS Amplify, please visit our documentation. For more details about these features, refer to our blog post.
Quelle: aws.amazon.com